List your company

Science on SciBench (Accuracy)

28.3Accuracy (SciBench)SC
13.94817.67421.425.126May 22, 2025

Evaluation results

MethodLinks
SCBackbone=Qwen-2.5-72B-Instruct2025.0528.3
AFlow-MathBackbone=Qwen-2.5-72B-Instruct2025.0528.3
SingleBackbone=Qwen-2.5-72B-Instruct2025.0528.1
MAS-GPTBackbone=Qwen-2.5-72B-Instruct2025.0528.1
SCBackbone=Llama-3.3-70B-Instruct2025.0527.9
DebateBackbone=Llama-3.3-70B-Instruct2025.0527.9
MAS-GPTBackbone=Llama-3.3-70B-Instruct2025.0526.9
DebateBackbone=Qwen-2.5-72B-Instruct2025.0526.9
MADBackbone=Qwen-2.5-72B-Instruct2025.0526.9
DyLANBackbone=Llama-3.3-70B-Instruct2025.0526.7
AutoGenBackbone=Qwen-2.5-72B-Instruct2025.0526.5
CoTBackbone=Qwen-2.5-72B-Instruct2025.0526.3
AgentVerseBackbone=Qwen-2.5-72B-Instruct2025.0525.9
AgentVerseBackbone=Llama-3.3-70B-Instruct2025.0525.7
SingleBackbone=Llama-3.3-70B-Instruct2025.0525.5
AFlow-MathBackbone=Llama-3.3-70B-Instruct2025.0525.3
MacNetBackbone=Qwen-2.5-72B-Instruct2025.0525.1
CoTBackbone=Llama-3.3-70B-Instruct2025.0524.7
DyLANBackbone=Qwen-2.5-72B-Instruct2025.0524.7
MAVBackbone=Llama-3.3-70B-Instruct2025.0524.3
MADBackbone=Llama-3.3-70B-Instruct2025.0523.7
MacNetBackbone=Llama-3.3-70B-Instruct2025.0523.5
AutoGenBackbone=Llama-3.3-70B-Instruct2025.0521.9
MAVBackbone=Qwen-2.5-72B-Instruct2025.0514.5